Commit graph

1599 commits

Author SHA1 Message Date
Ishaan Jaff
28a05fce3b fix test router debug logs 2024-05-06 16:38:16 -07:00
Ishaan Jaff
1d814a7234 fix add key name + team name in alerting messages 2024-05-06 14:29:04 -07:00
Krrish Dholakia
f1c2423ca4 fix(utils.py): handle gemini chunk no parts error
Fixes https://github.com/BerriAI/litellm/issues/3468
2024-05-06 10:59:53 -07:00
Simon Sanchez Viloria
9a95fa9348 Merge branch 'main' into feature/watsonx-integration 2024-05-06 17:27:14 +02:00
Simon Sanchez Viloria
361188b436 (feat) support for async stream to watsonx provider 2024-05-06 17:08:40 +02:00
Krrish Dholakia
80a1344c55 fix(utils.py): anthropic error handling 2024-05-06 07:25:12 -07:00
Alex Epstein
9ae08a8344 Update support for langfuse metadata
- Added ability to set trace release, version, metadata
- Added ability to update fields during a trace continuation
- Added ability to update input and output during a trace continuation
- Wrote new test for verifying metadata is set correctly
- Small improvement to setting secret boolean, prevent unnecessary literal_eval
- Small improvements to langfuse tests
2024-05-05 14:56:36 -04:00
Ishaan Jaff
edf8c9a04f fix don't return num retries in utils.py 2024-05-04 19:07:28 -07:00
Ishaan Jaff
7100ec0a67 feat return num retries in exceptions 2024-05-04 18:50:38 -07:00
Ishaan Jaff
adf09bdd45 fix add get_first_chars_messages in utils 2024-05-04 12:43:09 -07:00
Ishaan Jaff
bea785646f litellm map Azure GPT ContentPolicyViolationError 2024-05-04 11:14:47 -07:00
alisalim17
d40cadffef feat: add failure handler for logfire 2024-05-04 17:40:23 +04:00
alisalim17
785d781911 feat: add logfire integration 2024-05-04 16:22:53 +04:00
Sebastián Estévez
78890e2f33 add_function_to_prompt bug fix
This blows up when there's no "functions" in the dictionary even when tools is present because the inner function executes regardless (does not short circuit).
2024-05-03 23:38:54 -04:00
Krish Dholakia
0d3aa8d323 Merge pull request #3433 from BerriAI/litellm_timeout_fix
fix(bedrock.py): convert httpx.timeout to boto3 valid timeout
2024-05-03 18:53:59 -07:00
Krrish Dholakia
4efaacc5ce fix(anthropic.py): handle whitespace characters for anthropic calls 2024-05-03 17:31:34 -07:00
Krrish Dholakia
001e7976da docs(exception_mapping.md): update exception mapping docs with 'should_retry' 2024-05-03 16:51:26 -07:00
Ishaan Jaff
4819119823 Merge pull request #3432 from BerriAI/litellm_add_bedrock_titan_embed
Feat - add bedrock titan embed-v2
2024-05-03 16:28:12 -07:00
Krrish Dholakia
7715a9d333 fix(bedrock.py): convert httpx.timeout to boto3 valid timeout
Closes https://github.com/BerriAI/litellm/issues/3398
2024-05-03 16:24:21 -07:00
Ishaan Jaff
8943d7b3e6 test - bedrock v2 supports dimension 2024-05-03 16:23:37 -07:00
Ishaan Jaff
c468870c3d fix - support dimension for titan embed v2 2024-05-03 16:13:27 -07:00
Krrish Dholakia
aca36d8b79 feat(proxy_server.py): return api base in response headers
Closes https://github.com/BerriAI/litellm/issues/2631
2024-05-03 15:27:32 -07:00
Krrish Dholakia
d8446ffaf4 test(test_amazing_vertex_completion.py): try-except api errors 2024-05-03 10:09:57 -07:00
mogith-pn
c6f9cb9346 Clarifai - Added streaming and async completion support 2024-05-03 14:03:38 +00:00
Krish Dholakia
7e04447159 Merge pull request #3393 from Priva28/main
Add Llama3 tokenizer and allow custom tokenizers.
2024-05-02 16:32:41 -07:00
Ishaan Jaff
1dba007648 Merge pull request #3392 from BerriAI/litellm_fix_langfuse_reinitalized
[Fix] bug where langfuse was reinitialized on every call
2024-05-02 10:54:47 -07:00
Krrish Dholakia
6652e32869 fix(utils.py): revert pydantic object changes 2024-05-02 08:14:45 -07:00
Krrish Dholakia
c0487b16af fix(utils.py): add missing providers + models to validate_environment
Closes https://github.com/BerriAI/litellm/issues/3190
2024-05-02 08:14:45 -07:00
Krrish Dholakia
4fe55a28fc fix(utils.py): fix pydantic object default values 2024-05-01 22:51:46 -07:00
Christian Privitelli
8b4bc4c832 include methods in init import, add test, fix encode/decode param ordering 2024-05-02 15:49:22 +10:00
Krrish Dholakia
a241cdb818 fix(utils.py): fix default values 2024-05-01 22:24:37 -07:00
Christian Privitelli
f461f6b746 update docs, allow use with encode/decode 2024-05-02 14:56:38 +10:00
Krish Dholakia
14531ed6fa Merge pull request #3379 from elisalimli/main
[chore] Improve type-safety in Message & Delta classes
2024-05-01 21:19:52 -07:00
Krrish Dholakia
0b1382aef4 build(ui): enable adding openmeter via proxy ui 2024-05-01 21:16:23 -07:00
Christian Privitelli
2736a2c671 fix docs 2024-05-02 14:11:03 +10:00
Christian Privitelli
ff16701a4b add llama3 tokenizer and support for custom tokenizer 2024-05-02 14:05:38 +10:00
Ishaan Jaff
b818de3822 fix bug where langfuse was reinitialized 2024-05-01 20:47:25 -07:00
Krrish Dholakia
e7b3ac8e06 feat(openmeter.py): add support for user billing
open-meter supports user based billing. Closes https://github.com/BerriAI/litellm/issues/1268
2024-05-01 17:23:48 -07:00
Krrish Dholakia
b89f5aefb4 fix(utils.py): fix azure streaming content filter error chunk 2024-05-01 13:45:50 -07:00
Ishaan Jaff
ef53b2ecf2 Merge pull request #3384 from BerriAI/litellm_fix_details_to
fix - error sending details to log on sentry
2024-05-01 11:44:54 -07:00
Ishaan Jaff
b63dac8442 fix - error seeing details to log on sentry 2024-05-01 11:43:14 -07:00
Krrish Dholakia
abf14c61b3 fix(utils.py): check if response_object["choices"] is not none and iterable 2024-05-01 11:08:44 -07:00
Krrish Dholakia
b05fe5539e fix(utils.py): return received args for invalid model response object error
Addresses https://github.com/BerriAI/litellm/issues/3381
2024-05-01 10:47:26 -07:00
alisalim17
f676f53f6d set default tool calls and function call 2024-05-01 17:01:45 +04:00
alisalim17
fd069fc4f6 add tool_calls attribute to Message and Delta classes in order to improve type-safety 2024-05-01 13:47:01 +04:00
Krrish Dholakia
c18fb79761 fix(utils.py): add exception mapping for gemini error 2024-04-30 14:17:10 -07:00
Krrish Dholakia
701be55872 feat(utils.py): json logs for raw request sent by litellm
make it easier to view verbose logs in datadog
2024-04-29 19:21:19 -07:00
Krish Dholakia
f55d6b686b Merge pull request #3354 from BerriAI/litellm_replicate_cost_tracking
fix(utils.py): replicate now also has token based pricing for some models
2024-04-29 09:13:41 -07:00
Krrish Dholakia
2a88543f4d fix(utils.py): default to time-based tracking for unmapped replicate models. fix time-based cost calc for replicate 2024-04-29 08:36:01 -07:00
Krrish Dholakia
453f3d068d fix(utils.py): use llama tokenizer for replicate models 2024-04-29 08:28:31 -07:00